Liyao Xiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Liyao Xiang has a total of 101 co-authors. Here are the top co-authors by number of shared publications:
- Xinbing Wang
Shanghai Jiao Tong University, Shanghai, China
12 shared publications - Chenghu Zhou
Institute of Geographic Sciences and Natural Resources Research
6 shared publications Baochun Li
University of Toronto
4 shared publications- Jungang Yang
Shanghai Jiao Tong University, Shanghai, China
4 shared publications - Peng Tang
Shandong University, Qingdao, China
4 shared publications - Weidong Qiu
Shanghai Jiao Tong University
4 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23  (6) , 12541-12558
Efficient Linear and Secure Private Set Union and Its Applications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23  (6) , 12541-12558
Efficient Linear and Secure Private Set Union and Its Applications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3275-3286
PrivSniffer: Graph-based Contextual Privacy Leakage Detection for User-Generated Texts
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3275-3286
Open AccessPrivSniffer: Graph-based Contextual Privacy Leakage Detection for User-Generated Texts
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74  (00906778) , 3399-3411
DeepFP: Deep-Unfolded Fractional Programming for MIMO Beamforming
This work proposes a mixed learning-based and optimization-based approach to the weighted-sum-rates beamforming problem in a multiple-input multiple-output (MIMO) wireless network. The conventional methods, i.e., the fractional programming (FP) method and the weighted minimum mean square error (WMMSE) algorithm, can be computationally demanding for two reasons: (i) they require inverting a sequence of matrices whose sizes are proportional to the number of antennas; (ii) they require tuning a set of Lagrange multipliers to account for the power constraints. The recently proposed method called the reduced WMMSE addresses the above two issues for a single cell. In contrast, for the multicell case, another recent method called the FastFP eliminates the large matrix inversion and the Lagrange multipliers by using an improved FP technique, but the update stepsize in the FastFP can be difficult to decide. As such, we propose integrating the deep unfolding network into the FastFP for the stepsize optimization. Numerical experiments show that the proposed method is much more efficient than the learning method based on the WMMSE algorithm.
- 13 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74  (00906778) , 3399-3411
DeepFP: Deep-Unfolded Fractional Programming for MIMO Beamforming
This work proposes a mixed learning-based and optimization-based approach to the weighted-sum-rates beamforming problem in a multiple-input multiple-output (MIMO) wireless network. The conventional methods, i.e., the fractional programming (FP) method and the weighted minimum mean square error (WMMSE) algorithm, can be computationally demanding for two reasons: (i) they require inverting a sequence of matrices whose sizes are proportional to the number of antennas; (ii) they require tuning a set of Lagrange multipliers to account for the power constraints. The recently proposed method called the reduced WMMSE addresses the above two issues for a single cell. In contrast, for the multicell case, another recent method called the FastFP eliminates the large matrix inversion and the Lagrange multipliers by using an improved FP technique, but the update stepsize in the FastFP can be difficult to decide. As such, we propose integrating the deep unfolding network into the FastFP for the stepsize optimization. Numerical experiments show that the proposed method is much more efficient than the learning method based on the WMMSE algorithm.
- Open Access
DeepFP: Deep-Unfolded Fractional Programming for MIMO Beamforming
This work proposes a mixed learning-based and optimization-based approach to the weighted-sum-rates beamforming problem in a multiple-input multiple-output (MIMO) wireless network. The conventional methods, i.e., the fractional programming (FP) method and the weighted minimum mean square error (WMMSE) algorithm, can be computationally demanding for two reasons: (i) they require inverting a sequence of matrices whose sizes are proportional to the number of antennas; (ii) they require tuning a set of Lagrange multipliers to account for the power constraints. The recently proposed method called the reduced WMMSE addresses the above two issues for a single cell. In contrast, for the multicell case, another recent method called the FastFP eliminates the large matrix inversion and the Lagrange multipliers by using an improved FP technique, but the update stepsize in the FastFP can be difficult to decide. As such, we propose integrating the deep unfolding network into the FastFP for the stepsize optimization. Numerical experiments show that the proposed method is much more efficient than the learning method based on the WMMSE algorithm.
Open AccessDeepFP: Deep-Unfolded Fractional Programming for MIMO Beamforming
This work proposes a mixed learning-based and optimization-based approach to the weighted-sum-rates beamforming problem in a multiple-input multiple-output (MIMO) wireless network. The conventional methods, i.e., the fractional programming (FP) method and the weighted minimum mean square error (WMMSE) algorithm, can be computationally demanding for two reasons: (i) they require inverting a sequence of matrices whose sizes are proportional to the number of antennas; (ii) they require tuning a set of Lagrange multipliers to account for the power constraints. The recently proposed method called the reduced WMMSE addresses the above two issues for a single cell. In contrast, for the multicell case, another recent method called the FastFP eliminates the large matrix inversion and the Lagrange multipliers by using an improved FP technique, but the update stepsize in the FastFP can be difficult to decide. As such, we propose integrating the deep unfolding network into the FastFP for the stepsize optimization. Numerical experiments show that the proposed method is much more efficient than the learning method based on the WMMSE algorithm.
- Open Access
FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions
Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines.
Open AccessFedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions
Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for high-dimensional visual tasks. We propose FedTopo, a framework that integrates Topological-Guided Block Screening (TGBS) and Topological Embedding (TE) to leverage topological information, yielding coherently aligned cross-client representations by Topological Alignment Loss (TAL). First, Topology-Guided Block Screening (TGBS) automatically selects the most topology-informative block, i.e., the one with maximal topological separability, whose persistence-based signatures best distinguish within- versus between-class pairs, ensuring that subsequent analysis focuses on topology-rich features. Next, this block yields a compact Topological Embedding, which quantifies the topological information for each client. Finally, a Topological Alignment Loss (TAL) guides clients to maintain topological consistency with the global model during optimization, reducing representation drift across rounds. Experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under four non-I.I.D. partitions show that FedTopo accelerates convergence and improves accuracy over strong baselines.
- Open Access
PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
Watermarking schemes for large language models (LLMs) have been proposed to identify the source of the generated text, mitigating the potential threats emerged from model theft. However, current watermarking solutions hardly resolve the trust issue: the non-public watermark detection cannot prove itself faithfully conducting the detection. We observe that it is attributed to the secret key mostly used in the watermark detection -- it cannot be public, or the adversary may launch removal attacks provided the key; nor can it be private, or the watermarking detection is opaque to the public. To resolve the dilemma, we propose PVMark, a plugin based on zero-knowledge proof (ZKP), enabling the watermark detection process to be publicly verifiable by third parties without disclosing any secret key. PVMark hinges upon the proof of `correct execution' of watermark detection on which a set of ZKP constraints are built, including mapping, random number generation, comparison, and summation. We implement multiple variants of PVMark in Python, Rust and Circom, covering combinations of three watermarking schemes, three hash functions, and four ZKP protocols, to show our approach effectively works under a variety of circumstances. By experimental results, PVMark efficiently enables public verifiability on the state-of-the-art LLM watermarking schemes yet without compromising the watermarking performance, promising to be deployed in practice.
Open AccessPVMark: Enabling Public Verifiability for LLM Watermarking Schemes
Watermarking schemes for large language models (LLMs) have been proposed to identify the source of the generated text, mitigating the potential threats emerged from model theft. However, current watermarking solutions hardly resolve the trust issue: the non-public watermark detection cannot prove itself faithfully conducting the detection. We observe that it is attributed to the secret key mostly used in the watermark detection -- it cannot be public, or the adversary may launch removal attacks provided the key; nor can it be private, or the watermarking detection is opaque to the public. To resolve the dilemma, we propose PVMark, a plugin based on zero-knowledge proof (ZKP), enabling the watermark detection process to be publicly verifiable by third parties without disclosing any secret key. PVMark hinges upon the proof of `correct execution' of watermark detection on which a set of ZKP constraints are built, including mapping, random number generation, comparison, and summation. We implement multiple variants of PVMark in Python, Rust and Circom, covering combinations of three watermarking schemes, three hash functions, and four ZKP protocols, to show our approach effectively works under a variety of circumstances. By experimental results, PVMark efficiently enables public verifiability on the state-of-the-art LLM watermarking schemes yet without compromising the watermarking performance, promising to be deployed in practice.
- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47  (12) , 11051-11064
Interpretable Rotation-Equivariant Multiary-Valued Network for Attribute Obfuscation
This paper focuses on the problem of preventing information leakage in neural networks, i.e., assuming that attackers have obtained intermediate-layer features of a neural network, and preventing attackers from inverting these features to the input with private information. We propose a generic method to slightly revise each arbitrary traditional neural network into a multiary-valued rotation-equivariant neural network (RENN) for preventing information leakage. Specifically, we convert real-valued features in the network into multi-ary features, and each element in the feature vector is a multi-ary number. We hide the input information into a certain phase of the multi-ary feature, and rotate the multi-ary feature for attribute obfuscation in the encryption process. The rotation axis and angle can be considered as the private key. In this way, even when attackers have obtained network parameters and intermediate-layer features, they still cannot extract input information without knowing the rotation information. More crucially, the encryption operation does not damage the spatial correlations between features, so that the encrypted features can be easily processed by convolution operations in the neural network without difficulties. In order to implement successful encryption and decryption, the RENN is designed to satisfy the rotation equivariance property. To this end, we propose a set of rules to revise classic operations in the neural network to ensure the rotation equivariance property. Besides, we prove that the$d$ -ary RENN is downward compatible with the$d^{\prime }$ -ary RENN when$d^{\prime }< d$ . In experiments, the RENN significantly boosts the capacity of preventing information leakage, yet with only mild degradation of classification accuracy, compared to traditional neural networks. Besides, the computational cost is much less than the homomorphic encryption.- 15 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47  (12) , 11051-11064
Interpretable Rotation-Equivariant Multiary-Valued Network for Attribute Obfuscation
This paper focuses on the problem of preventing information leakage in neural networks, i.e., assuming that attackers have obtained intermediate-layer features of a neural network, and preventing attackers from inverting these features to the input with private information. We propose a generic method to slightly revise each arbitrary traditional neural network into a multiary-valued rotation-equivariant neural network (RENN) for preventing information leakage. Specifically, we convert real-valued features in the network into multi-ary features, and each element in the feature vector is a multi-ary number. We hide the input information into a certain phase of the multi-ary feature, and rotate the multi-ary feature for attribute obfuscation in the encryption process. The rotation axis and angle can be considered as the private key. In this way, even when attackers have obtained network parameters and intermediate-layer features, they still cannot extract input information without knowing the rotation information. More crucially, the encryption operation does not damage the spatial correlations between features, so that the encrypted features can be easily processed by convolution operations in the neural network without difficulties. In order to implement successful encryption and decryption, the RENN is designed to satisfy the rotation equivariance property. To this end, we propose a set of rules to revise classic operations in the neural network to ensure the rotation equivariance property. Besides, we prove that the$d$ -ary RENN is downward compatible with the$d^{\prime }$ -ary RENN when$d^{\prime }< d$ . In experiments, the RENN significantly boosts the capacity of preventing information leakage, yet with only mild degradation of classification accuracy, compared to traditional neural networks. Besides, the computational cost is much less than the homomorphic encryption.- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22  (6) , 7614-7631
Privacy-Preserving Authorized Set Matching via Dishonest Majority Multiparty Computation
Private Set Intersection (PSI) enables each party with a private set to compute the intersection without disclosing other information. However, even in maliciously secure PSI, it does not guarantee input authenticity and output integrity, which becomes problematic in certain scenarios. For instance, in Web 3.0, one of the essential requirements is to find common certifiers among the parties. However, if certifier identities are meant to be protected, some parties may attempt to forge certifier identities or intentionally exclude a particular certifier during protocol execution. Recently, the Private Certifier Intersection (PCI), a variant of PSI, has been proposed to address this problem. Nevertheless, it incurs significantly high computational and communication overhead. This work proposes the Private Identity Intersection (PII), which takes private identifiers and corresponding anonymous signatures from mutually distrusting parties as input, verifies them, and delivers the intersection of the successfully verified identifiers to all parties while ensuring the integrity of the output. Furthermore, PII can naturally extend from two to multiple-party settings while resisting the collusion attack. To achieve the ideal functionality of PII, we implement a user-friendly MPC framework called Oryx without third-party libraries. Based on Oryx, we instantiate PII with two digital signature schemes, one proposed in this paper. Compared to existing work, our PII protocols reduce the computation overhead by up to 163× and the communication overhead by up to 190×, representing an improvement of two orders of magnitude. To demonstrate the practicality of our work, we evaluate its performance in WAN environments with bandwidths of 100 Mbps and 500 Mbps, under a fixed latency of 20 ms. All implementations are available at: https://github.com/ShallMate/Oryx.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22  (6) , 7614-7631
Privacy-Preserving Authorized Set Matching via Dishonest Majority Multiparty Computation
Private Set Intersection (PSI) enables each party with a private set to compute the intersection without disclosing other information. However, even in maliciously secure PSI, it does not guarantee input authenticity and output integrity, which becomes problematic in certain scenarios. For instance, in Web 3.0, one of the essential requirements is to find common certifiers among the parties. However, if certifier identities are meant to be protected, some parties may attempt to forge certifier identities or intentionally exclude a particular certifier during protocol execution. Recently, the Private Certifier Intersection (PCI), a variant of PSI, has been proposed to address this problem. Nevertheless, it incurs significantly high computational and communication overhead. This work proposes the Private Identity Intersection (PII), which takes private identifiers and corresponding anonymous signatures from mutually distrusting parties as input, verifies them, and delivers the intersection of the successfully verified identifiers to all parties while ensuring the integrity of the output. Furthermore, PII can naturally extend from two to multiple-party settings while resisting the collusion attack. To achieve the ideal functionality of PII, we implement a user-friendly MPC framework called Oryx without third-party libraries. Based on Oryx, we instantiate PII with two digital signature schemes, one proposed in this paper. Compared to existing work, our PII protocols reduce the computation overhead by up to 163× and the communication overhead by up to 190×, representing an improvement of two orders of magnitude. To demonstrate the practicality of our work, we evaluate its performance in WAN environments with bandwidths of 100 Mbps and 500 Mbps, under a fixed latency of 20 ms. All implementations are available at: https://github.com/ShallMate/Oryx.
- Open Access
Graph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach
Graph unlearning is tailored for GNNs to handle widespread and various graph structure unlearning requests, which remain largely unexplored. The GIF (graph influence function) achieves validity under partial edge unlearning, but faces challenges in dealing with more disturbing node unlearning. To avoid the overhead of retraining and realize the model utility of unlearning, we proposed a novel node unlearning method to reverse the process of aggregation in GNN by embedding reconstruction and to adopt Range-Null Space Decomposition for the nodes' interaction learning. Experimental results on multiple representative datasets demonstrate the SOTA performance of our proposed approach.
Open AccessGraph Unlearning via Embedding Reconstruction -- A Range-Null Space Decomposition Approach
Graph unlearning is tailored for GNNs to handle widespread and various graph structure unlearning requests, which remain largely unexplored. The GIF (graph influence function) achieves validity under partial edge unlearning, but faces challenges in dealing with more disturbing node unlearning. To avoid the overhead of retraining and realize the model utility of unlearning, we proposed a novel node unlearning method to reverse the process of aggregation in GNN by embedding reconstruction and to adopt Range-Null Space Decomposition for the nodes' interaction learning. Experimental results on multiple representative datasets demonstrate the SOTA performance of our proposed approach.
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22  (6) , 7077-7090
CodeMark : Contextual and Natural Watermarking for Tracing Code Snippet Provenance
Determining the origins of code snippets has gained increasing attention due to the popularity of large language models and the concern about their misuse in generating unlicensed or malicious code. Watermarking is considered a working solution for tracing code snippet provenance. However, source code watermarking requires more stringent and intricate rules than natural language or software watermarking, since one needs to ensure both readability and functionality of the watermarked code snippets. To this end, we propose a novel watermarking system CodeMark, featured by variable renaming as the key. Surrounding variable renaming, several challenges emerge such as determining renaming candidates, defining the variable context, and providing diverse variable substitutes, etc. The design of CodeMark conquers these challenges by an end-to-end learning system, which interprets the code context through Graph Neural Networks (GNNs) and generates natural substitutes fitting the context by distilling from CodeBERT. Experiments illustrate that CodeMark surpasses the state-of-the-art watermarking systems in terms of watermarking requirements.
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22  (6) , 7077-7090
CodeMark : Contextual and Natural Watermarking for Tracing Code Snippet Provenance
Determining the origins of code snippets has gained increasing attention due to the popularity of large language models and the concern about their misuse in generating unlicensed or malicious code. Watermarking is considered a working solution for tracing code snippet provenance. However, source code watermarking requires more stringent and intricate rules than natural language or software watermarking, since one needs to ensure both readability and functionality of the watermarked code snippets. To this end, we propose a novel watermarking system CodeMark, featured by variable renaming as the key. Surrounding variable renaming, several challenges emerge such as determining renaming candidates, defining the variable context, and providing diverse variable substitutes, etc. The design of CodeMark conquers these challenges by an end-to-end learning system, which interprets the code context through Graph Neural Networks (GNNs) and generates natural substitutes fitting the context by distilling from CodeBERT. Experiments illustrate that CodeMark surpasses the state-of-the-art watermarking systems in terms of watermarking requirements.